print("Creating dataset")
# index of examples dataset
dataset_index = corpora_tools.from_indexable(
torch.arange(0, len(D), 1).unsqueeze(-1))
D.set_path(False)
# random walk dataset
d_rw = D.light_copy()
d_rw.set_walk(parameters.walk_length, 1.0)
d_rw.set_path(True)
# neigbhor dataset
d_v = D.light_copy()
d_v.set_walk(1, 1.0)
print("Merging dataset")
embedding_dataset = corpora_tools.zip_datasets(
dataset_index, corpora_tools.select_from_index(d_rw, element_index=0),
corpora_tools.select_from_index(d_v, element_index=0))
training_dataloader = DataLoader(embedding_dataset,
batch_size=128,
shuffle=True,
num_workers=4,
collate_fn=data_tools.PadCollate(dim=0),
drop_last=False)
print("Initialize embeddings")
hyperbolic_embeddings_graph.learn_init(embeddings,
training_dataloader,
embedding_dataset,
optimizer_method,
modules.hyperbolicDistance,
max_iter=150,
d_rw.set_path(True)
d_rw = corpora.FlatContextCorpus(d_rw, context_size=args.context_size, precompute=args.precompute_rw)
torch.save(d_rw, "/local/gerald/KMEANS_RESULTS/"+key+".t7")
rw_log[key] = {"file":"/local/gerald/KMEANS_RESULTS/"+key+".t7",
"context_size":args.context_size, "walk_lenght": args.walk_lenght,
"precompute_rw": args.precompute_rw}
else:
d_rw.set_walk(args.walk_lenght, 1.0)
d_rw.set_path(True)
d_rw = corpora.ContextCorpus(d_rw, context_size=args.context_size, precompute=args.precompute_rw)
# neigbhor dataset
d_v = D.light_copy()
d_v.set_walk(1, 1.0)
dataset_repeated = corpora_tools.zip_datasets(dataset_index, corpora_tools.select_from_index(d_v, element_index=0))
dataset_repeated = corpora_tools.repeat_dataset(dataset_repeated, len(d_rw))
# print(d_rw[1][0].size())
print("Merging dataset")
embedding_dataset = corpora_tools.zip_datasets(dataset_repeated, d_rw)
training_dataloader = DataLoader(embedding_dataset,
batch_size=args.batch_size,
shuffle=False,
num_workers=4,
drop_last=False
)
representation_d = []
d_rw.set_walk(args.walk_lenght, 1.0)
d_rw.set_path(True)
d_rw = corpora.ContextCorpus(d_rw, context_size=args.context_size, precompute=args.precompute_rw)
if(args.save):
os.makedirs("/local/gerald/AISTAT_RESULTS/"+args.id+"/", exist_ok=True)
logger_object = logger.JSONLogger("/local/gerald/AISTAT_RESULTS/"+args.id+"/log.json")
logger_object.append(vars(args))
# neigbhor dataset
d_v = D.light_copy()
d_v.set_walk(1, 1.0)
print(d_rw[1][0].size())
print("Merging dataset")
embedding_dataset = corpora_tools.zip_datasets(dataset_index,
corpora_tools.select_from_index(d_v, element_index=0),
d_rw
)
print(embedding_dataset[29][-1][20:25])
training_dataloader = DataLoader(embedding_dataset,
batch_size=args.batch_size,
shuffle=False,
num_workers=8,
collate_fn=data_tools.PadCollate(dim=0),
drop_last=False
)
representation_d = []
pi_d = []
mu_d = []
sigma_d = []
